© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 115707
    Prev
    Next
    INDEX
    Explanations

    personal descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nông
    -0.07
    다가
    -0.07
    假
    -0.07
     víctima
    -0.07
     право
    -0.07
    -shirts
    -0.06
    专业
    -0.06
     нарушен
    -0.06
     sabotage
    -0.06
     marijuana
    -0.06
    POSITIVE LOGITS
     السلام
    0.08
     Stops
    0.08
    held
    0.07
    alez
    0.07
    的例子
    0.07
     eof
    0.07
    clud
    0.07
    _leg
    0.07
    obuf
    0.07
    here
    0.07
    Activations Density 0.044%

    No Known Activations